Abstract
Endmember variability is receiving growing attention in the hyperspectral image (HSI) unmixing field. As an extension of linear mixing model (LMM), normal compositional model (NCM) assumes that the pixels of the HSI are linear combinations of random endmembers (as opposed to deterministic for the LMM). NCM explains spectral differences between the observed pixels and endmembers as endmember mixtures and endmember variances, the characteristic of which makes it possible to incorporate the endmember spectral variability in the unmixing process. But the tricky issue for using NCM is the estimation of endmember variances inhering in materials. This letter presents a new approach, termed region-based stochastic expectation maximization, to learn endmember variances from spatial information. The idea is assuming that significant homogeneous regions (composed of similar materials or similar mixture) exist in the HSI, such regions usually give visual indication that spatial-based spectral variability really exists in hyperspectral data. As modeled in NCM, spectral variances in homogeneous region can be approximately linear represented by endmember variances. Hence, given region-based spectral variances, we are able to learn endmember variances. In experiments with simulated data and Moffett field data, the proposed approach competes with other unmixing methods considering endmember variability, with better endmember variance estimates.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.